ryanmarten commited on
Commit
b53a004
·
verified ·
1 Parent(s): 9282d12

Training in progress, epoch 3

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1849431bd1611811dbcafa5affdde6dfa37a7c02c37a8506699f18f88993f6b7
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:875efa837cd331fd43d2993bbd83b08257739e0b1276bd7e34b7b56d5805abfe
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6333f47f7d8c39e64339300418afa0e6daf6ac5f21e6f995474eeb791628c318
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6aa8588cff67881cfb47f3c32ca19e582c93e4b0c43e2df5e32053bfffecac28
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f445c7fb9ba2a189192877a2097ecdaa9b61c1a5f221fe2560da04f2066349a9
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9eb5a9229148887c187aa6cb1ee0f36fe8dc1547d199252f609a0b2e3f81832
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:33059ca950a6e0dd1cd7bb4bc1ec0ecb6731cfac4fc39cbca211704fa9a01cad
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b71e8b7f634c37d8877b40f84751f01f9eca8d41ea2e5eea88d07f88e1efa655
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -234,3 +234,81 @@
234
  {"current_steps": 233, "total_steps": 390, "loss": 0.5114, "lr": 1.6703461793876876e-05, "epoch": 2.9824, "percentage": 59.74, "elapsed_time": "10:35:56", "remaining_time": "7:08:30"}
235
  {"current_steps": 234, "total_steps": 390, "loss": 0.5212, "lr": 1.6527036446661396e-05, "epoch": 2.9952, "percentage": 60.0, "elapsed_time": "10:38:40", "remaining_time": "7:05:46"}
236
  {"current_steps": 235, "total_steps": 390, "loss": 0.4906, "lr": 1.635088931591775e-05, "epoch": 3.008, "percentage": 60.26, "elapsed_time": "10:42:26", "remaining_time": "7:03:44"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
234
  {"current_steps": 233, "total_steps": 390, "loss": 0.5114, "lr": 1.6703461793876876e-05, "epoch": 2.9824, "percentage": 59.74, "elapsed_time": "10:35:56", "remaining_time": "7:08:30"}
235
  {"current_steps": 234, "total_steps": 390, "loss": 0.5212, "lr": 1.6527036446661396e-05, "epoch": 2.9952, "percentage": 60.0, "elapsed_time": "10:38:40", "remaining_time": "7:05:46"}
236
  {"current_steps": 235, "total_steps": 390, "loss": 0.4906, "lr": 1.635088931591775e-05, "epoch": 3.008, "percentage": 60.26, "elapsed_time": "10:42:26", "remaining_time": "7:03:44"}
237
+ {"current_steps": 236, "total_steps": 390, "loss": 0.4553, "lr": 1.6175034512658753e-05, "epoch": 3.0208, "percentage": 60.51, "elapsed_time": "10:45:13", "remaining_time": "7:01:02"}
238
+ {"current_steps": 237, "total_steps": 390, "loss": 0.454, "lr": 1.5999486124479115e-05, "epoch": 3.0336, "percentage": 60.77, "elapsed_time": "10:47:52", "remaining_time": "6:58:15"}
239
+ {"current_steps": 238, "total_steps": 390, "loss": 0.4601, "lr": 1.5824258214426833e-05, "epoch": 3.0464, "percentage": 61.03, "elapsed_time": "10:50:30", "remaining_time": "6:55:26"}
240
+ {"current_steps": 239, "total_steps": 390, "loss": 0.471, "lr": 1.5649364819876655e-05, "epoch": 3.0592, "percentage": 61.28, "elapsed_time": "10:53:26", "remaining_time": "6:52:50"}
241
+ {"current_steps": 240, "total_steps": 390, "loss": 0.4619, "lr": 1.547481995140556e-05, "epoch": 3.072, "percentage": 61.54, "elapsed_time": "10:55:59", "remaining_time": "6:49:59"}
242
+ {"current_steps": 241, "total_steps": 390, "loss": 0.4714, "lr": 1.5300637591670357e-05, "epoch": 3.0848, "percentage": 61.79, "elapsed_time": "10:58:44", "remaining_time": "6:47:16"}
243
+ {"current_steps": 242, "total_steps": 390, "loss": 0.4487, "lr": 1.5126831694287564e-05, "epoch": 3.0976, "percentage": 62.05, "elapsed_time": "11:01:25", "remaining_time": "6:44:30"}
244
+ {"current_steps": 243, "total_steps": 390, "loss": 0.4881, "lr": 1.4953416182715566e-05, "epoch": 3.1104, "percentage": 62.31, "elapsed_time": "11:04:17", "remaining_time": "6:41:51"}
245
+ {"current_steps": 244, "total_steps": 390, "loss": 0.465, "lr": 1.478040494913926e-05, "epoch": 3.1232, "percentage": 62.56, "elapsed_time": "11:07:07", "remaining_time": "6:39:11"}
246
+ {"current_steps": 245, "total_steps": 390, "loss": 0.4477, "lr": 1.460781185335713e-05, "epoch": 3.136, "percentage": 62.82, "elapsed_time": "11:09:38", "remaining_time": "6:36:18"}
247
+ {"current_steps": 246, "total_steps": 390, "loss": 0.4608, "lr": 1.443565072167095e-05, "epoch": 3.1488, "percentage": 63.08, "elapsed_time": "11:12:16", "remaining_time": "6:33:31"}
248
+ {"current_steps": 247, "total_steps": 390, "loss": 0.4537, "lr": 1.4263935345778202e-05, "epoch": 3.1616, "percentage": 63.33, "elapsed_time": "11:14:59", "remaining_time": "6:30:46"}
249
+ {"current_steps": 248, "total_steps": 390, "loss": 0.4671, "lr": 1.409267948166718e-05, "epoch": 3.1744, "percentage": 63.59, "elapsed_time": "11:17:36", "remaining_time": "6:27:58"}
250
+ {"current_steps": 249, "total_steps": 390, "loss": 0.4523, "lr": 1.3921896848515064e-05, "epoch": 3.1872, "percentage": 63.85, "elapsed_time": "11:20:03", "remaining_time": "6:25:05"}
251
+ {"current_steps": 250, "total_steps": 390, "loss": 0.4448, "lr": 1.3751601127588849e-05, "epoch": 3.2, "percentage": 64.1, "elapsed_time": "11:22:48", "remaining_time": "6:22:22"}
252
+ {"current_steps": 251, "total_steps": 390, "loss": 0.4551, "lr": 1.3581805961149371e-05, "epoch": 3.2128, "percentage": 64.36, "elapsed_time": "11:25:33", "remaining_time": "6:19:38"}
253
+ {"current_steps": 252, "total_steps": 390, "loss": 0.4471, "lr": 1.341252495135841e-05, "epoch": 3.2256, "percentage": 64.62, "elapsed_time": "11:28:03", "remaining_time": "6:16:47"}
254
+ {"current_steps": 253, "total_steps": 390, "loss": 0.4467, "lr": 1.324377165918906e-05, "epoch": 3.2384, "percentage": 64.87, "elapsed_time": "11:30:42", "remaining_time": "6:14:00"}
255
+ {"current_steps": 254, "total_steps": 390, "loss": 0.4422, "lr": 1.3075559603339354e-05, "epoch": 3.2512, "percentage": 65.13, "elapsed_time": "11:33:24", "remaining_time": "6:11:16"}
256
+ {"current_steps": 255, "total_steps": 390, "loss": 0.4526, "lr": 1.2907902259149287e-05, "epoch": 3.2640000000000002, "percentage": 65.38, "elapsed_time": "11:36:04", "remaining_time": "6:08:30"}
257
+ {"current_steps": 256, "total_steps": 390, "loss": 0.4606, "lr": 1.274081305752135e-05, "epoch": 3.2768, "percentage": 65.64, "elapsed_time": "11:38:36", "remaining_time": "6:05:40"}
258
+ {"current_steps": 257, "total_steps": 390, "loss": 0.4624, "lr": 1.2574305383844528e-05, "epoch": 3.2896, "percentage": 65.9, "elapsed_time": "11:41:15", "remaining_time": "6:02:54"}
259
+ {"current_steps": 258, "total_steps": 390, "loss": 0.4488, "lr": 1.2408392576922075e-05, "epoch": 3.3024, "percentage": 66.15, "elapsed_time": "11:43:49", "remaining_time": "6:00:05"}
260
+ {"current_steps": 259, "total_steps": 390, "loss": 0.4703, "lr": 1.2243087927902905e-05, "epoch": 3.3152, "percentage": 66.41, "elapsed_time": "11:46:20", "remaining_time": "5:57:15"}
261
+ {"current_steps": 260, "total_steps": 390, "loss": 0.4415, "lr": 1.2078404679216864e-05, "epoch": 3.328, "percentage": 66.67, "elapsed_time": "11:49:01", "remaining_time": "5:54:30"}
262
+ {"current_steps": 261, "total_steps": 390, "loss": 0.4519, "lr": 1.1914356023513904e-05, "epoch": 3.3407999999999998, "percentage": 66.92, "elapsed_time": "11:51:41", "remaining_time": "5:51:45"}
263
+ {"current_steps": 262, "total_steps": 390, "loss": 0.4592, "lr": 1.1750955102607193e-05, "epoch": 3.3536, "percentage": 67.18, "elapsed_time": "11:54:33", "remaining_time": "5:49:05"}
264
+ {"current_steps": 263, "total_steps": 390, "loss": 0.457, "lr": 1.1588215006420374e-05, "epoch": 3.3664, "percentage": 67.44, "elapsed_time": "11:57:27", "remaining_time": "5:46:27"}
265
+ {"current_steps": 264, "total_steps": 390, "loss": 0.4661, "lr": 1.1426148771938915e-05, "epoch": 3.3792, "percentage": 67.69, "elapsed_time": "12:00:10", "remaining_time": "5:43:43"}
266
+ {"current_steps": 265, "total_steps": 390, "loss": 0.4341, "lr": 1.1264769382165748e-05, "epoch": 3.392, "percentage": 67.95, "elapsed_time": "12:03:02", "remaining_time": "5:41:03"}
267
+ {"current_steps": 266, "total_steps": 390, "loss": 0.4523, "lr": 1.110408976508118e-05, "epoch": 3.4048, "percentage": 68.21, "elapsed_time": "12:05:56", "remaining_time": "5:38:24"}
268
+ {"current_steps": 267, "total_steps": 390, "loss": 0.4591, "lr": 1.094412279260726e-05, "epoch": 3.4176, "percentage": 68.46, "elapsed_time": "12:08:34", "remaining_time": "5:35:38"}
269
+ {"current_steps": 268, "total_steps": 390, "loss": 0.4519, "lr": 1.0784881279576635e-05, "epoch": 3.4304, "percentage": 68.72, "elapsed_time": "12:11:31", "remaining_time": "5:33:00"}
270
+ {"current_steps": 269, "total_steps": 390, "loss": 0.4525, "lr": 1.0626377982705929e-05, "epoch": 3.4432, "percentage": 68.97, "elapsed_time": "12:14:12", "remaining_time": "5:30:15"}
271
+ {"current_steps": 270, "total_steps": 390, "loss": 0.4643, "lr": 1.0468625599573842e-05, "epoch": 3.456, "percentage": 69.23, "elapsed_time": "12:16:42", "remaining_time": "5:27:25"}
272
+ {"current_steps": 271, "total_steps": 390, "loss": 0.4458, "lr": 1.0311636767603952e-05, "epoch": 3.4688, "percentage": 69.49, "elapsed_time": "12:19:22", "remaining_time": "5:24:40"}
273
+ {"current_steps": 272, "total_steps": 390, "loss": 0.4512, "lr": 1.0155424063052306e-05, "epoch": 3.4816, "percentage": 69.74, "elapsed_time": "12:22:14", "remaining_time": "5:22:00"}
274
+ {"current_steps": 273, "total_steps": 390, "loss": 0.4686, "lr": 1.0000000000000006e-05, "epoch": 3.4944, "percentage": 70.0, "elapsed_time": "12:25:02", "remaining_time": "5:19:18"}
275
+ {"current_steps": 274, "total_steps": 390, "loss": 0.4536, "lr": 9.84537702935065e-06, "epoch": 3.5072, "percentage": 70.26, "elapsed_time": "12:27:44", "remaining_time": "5:16:33"}
276
+ {"current_steps": 275, "total_steps": 390, "loss": 0.462, "lr": 9.691567537832964e-06, "epoch": 3.52, "percentage": 70.51, "elapsed_time": "12:30:31", "remaining_time": "5:13:51"}
277
+ {"current_steps": 276, "total_steps": 390, "loss": 0.4429, "lr": 9.538583847008452e-06, "epoch": 3.5328, "percentage": 70.77, "elapsed_time": "12:33:17", "remaining_time": "5:11:08"}
278
+ {"current_steps": 277, "total_steps": 390, "loss": 0.4694, "lr": 9.386438212284372e-06, "epoch": 3.5456, "percentage": 71.03, "elapsed_time": "12:36:02", "remaining_time": "5:08:25"}
279
+ {"current_steps": 278, "total_steps": 390, "loss": 0.4628, "lr": 9.235142821931928e-06, "epoch": 3.5584, "percentage": 71.28, "elapsed_time": "12:38:36", "remaining_time": "5:05:37"}
280
+ {"current_steps": 279, "total_steps": 390, "loss": 0.4647, "lr": 9.084709796109907e-06, "epoch": 3.5712, "percentage": 71.54, "elapsed_time": "12:41:17", "remaining_time": "5:02:52"}
281
+ {"current_steps": 280, "total_steps": 390, "loss": 0.472, "lr": 8.93515118589373e-06, "epoch": 3.584, "percentage": 71.79, "elapsed_time": "12:44:00", "remaining_time": "5:00:08"}
282
+ {"current_steps": 281, "total_steps": 390, "loss": 0.4602, "lr": 8.786478972310023e-06, "epoch": 3.5968, "percentage": 72.05, "elapsed_time": "12:46:40", "remaining_time": "4:57:23"}
283
+ {"current_steps": 282, "total_steps": 390, "loss": 0.4512, "lr": 8.638705065376887e-06, "epoch": 3.6096, "percentage": 72.31, "elapsed_time": "12:49:28", "remaining_time": "4:54:41"}
284
+ {"current_steps": 283, "total_steps": 390, "loss": 0.4484, "lr": 8.491841303149728e-06, "epoch": 3.6224, "percentage": 72.56, "elapsed_time": "12:52:10", "remaining_time": "4:51:57"}
285
+ {"current_steps": 284, "total_steps": 390, "loss": 0.4444, "lr": 8.345899450772975e-06, "epoch": 3.6352, "percentage": 72.82, "elapsed_time": "12:54:47", "remaining_time": "4:49:10"}
286
+ {"current_steps": 285, "total_steps": 390, "loss": 0.4513, "lr": 8.200891199537549e-06, "epoch": 3.648, "percentage": 73.08, "elapsed_time": "12:57:21", "remaining_time": "4:46:23"}
287
+ {"current_steps": 286, "total_steps": 390, "loss": 0.4466, "lr": 8.056828165944282e-06, "epoch": 3.6608, "percentage": 73.33, "elapsed_time": "12:59:56", "remaining_time": "4:43:36"}
288
+ {"current_steps": 287, "total_steps": 390, "loss": 0.4663, "lr": 7.913721890773354e-06, "epoch": 3.6736, "percentage": 73.59, "elapsed_time": "13:02:42", "remaining_time": "4:40:54"}
289
+ {"current_steps": 288, "total_steps": 390, "loss": 0.446, "lr": 7.771583838159756e-06, "epoch": 3.6864, "percentage": 73.85, "elapsed_time": "13:05:15", "remaining_time": "4:38:06"}
290
+ {"current_steps": 289, "total_steps": 390, "loss": 0.4723, "lr": 7.630425394674903e-06, "epoch": 3.6992000000000003, "percentage": 74.1, "elapsed_time": "13:07:51", "remaining_time": "4:35:20"}
291
+ {"current_steps": 290, "total_steps": 390, "loss": 0.468, "lr": 7.49025786841445e-06, "epoch": 3.7119999999999997, "percentage": 74.36, "elapsed_time": "13:10:45", "remaining_time": "4:32:40"}
292
+ {"current_steps": 291, "total_steps": 390, "loss": 0.4662, "lr": 7.3510924880924575e-06, "epoch": 3.7248, "percentage": 74.62, "elapsed_time": "13:13:32", "remaining_time": "4:29:57"}
293
+ {"current_steps": 292, "total_steps": 390, "loss": 0.456, "lr": 7.212940402141808e-06, "epoch": 3.7376, "percentage": 74.87, "elapsed_time": "13:16:18", "remaining_time": "4:27:15"}
294
+ {"current_steps": 293, "total_steps": 390, "loss": 0.4386, "lr": 7.075812677821145e-06, "epoch": 3.7504, "percentage": 75.13, "elapsed_time": "13:18:52", "remaining_time": "4:24:28"}
295
+ {"current_steps": 294, "total_steps": 390, "loss": 0.4441, "lr": 6.939720300328303e-06, "epoch": 3.7632, "percentage": 75.38, "elapsed_time": "13:21:30", "remaining_time": "4:21:42"}
296
+ {"current_steps": 295, "total_steps": 390, "loss": 0.4503, "lr": 6.8046741719202385e-06, "epoch": 3.776, "percentage": 75.64, "elapsed_time": "13:24:09", "remaining_time": "4:18:57"}
297
+ {"current_steps": 296, "total_steps": 390, "loss": 0.4538, "lr": 6.67068511103971e-06, "epoch": 3.7888, "percentage": 75.9, "elapsed_time": "13:26:50", "remaining_time": "4:16:13"}
298
+ {"current_steps": 297, "total_steps": 390, "loss": 0.4527, "lr": 6.537763851448593e-06, "epoch": 3.8016, "percentage": 76.15, "elapsed_time": "13:29:29", "remaining_time": "4:13:28"}
299
+ {"current_steps": 298, "total_steps": 390, "loss": 0.4583, "lr": 6.4059210413680175e-06, "epoch": 3.8144, "percentage": 76.41, "elapsed_time": "13:31:56", "remaining_time": "4:10:40"}
300
+ {"current_steps": 299, "total_steps": 390, "loss": 0.4373, "lr": 6.275167242625331e-06, "epoch": 3.8272, "percentage": 76.67, "elapsed_time": "13:34:38", "remaining_time": "4:07:56"}
301
+ {"current_steps": 300, "total_steps": 390, "loss": 0.4692, "lr": 6.145512929808013e-06, "epoch": 3.84, "percentage": 76.92, "elapsed_time": "13:37:26", "remaining_time": "4:05:13"}
302
+ {"current_steps": 301, "total_steps": 390, "loss": 0.4558, "lr": 6.016968489424572e-06, "epoch": 3.8528000000000002, "percentage": 77.18, "elapsed_time": "13:40:09", "remaining_time": "4:02:30"}
303
+ {"current_steps": 302, "total_steps": 390, "loss": 0.4711, "lr": 5.889544219072465e-06, "epoch": 3.8656, "percentage": 77.44, "elapsed_time": "13:42:53", "remaining_time": "3:59:46"}
304
+ {"current_steps": 303, "total_steps": 390, "loss": 0.4354, "lr": 5.7632503266131925e-06, "epoch": 3.8784, "percentage": 77.69, "elapsed_time": "13:45:36", "remaining_time": "3:57:03"}
305
+ {"current_steps": 304, "total_steps": 390, "loss": 0.469, "lr": 5.638096929354522e-06, "epoch": 3.8912, "percentage": 77.95, "elapsed_time": "13:48:25", "remaining_time": "3:54:21"}
306
+ {"current_steps": 305, "total_steps": 390, "loss": 0.4586, "lr": 5.514094053240035e-06, "epoch": 3.904, "percentage": 78.21, "elapsed_time": "13:50:54", "remaining_time": "3:51:33"}
307
+ {"current_steps": 306, "total_steps": 390, "loss": 0.443, "lr": 5.39125163204594e-06, "epoch": 3.9168, "percentage": 78.46, "elapsed_time": "13:53:33", "remaining_time": "3:48:49"}
308
+ {"current_steps": 307, "total_steps": 390, "loss": 0.453, "lr": 5.269579506585259e-06, "epoch": 3.9295999999999998, "percentage": 78.72, "elapsed_time": "13:56:06", "remaining_time": "3:46:02"}
309
+ {"current_steps": 308, "total_steps": 390, "loss": 0.4607, "lr": 5.149087423919541e-06, "epoch": 3.9424, "percentage": 78.97, "elapsed_time": "13:58:58", "remaining_time": "3:43:21"}
310
+ {"current_steps": 309, "total_steps": 390, "loss": 0.4514, "lr": 5.029785036577976e-06, "epoch": 3.9552, "percentage": 79.23, "elapsed_time": "14:01:35", "remaining_time": "3:40:36"}
311
+ {"current_steps": 310, "total_steps": 390, "loss": 0.4487, "lr": 4.911681901784198e-06, "epoch": 3.968, "percentage": 79.49, "elapsed_time": "14:04:14", "remaining_time": "3:37:52"}
312
+ {"current_steps": 311, "total_steps": 390, "loss": 0.442, "lr": 4.794787480690597e-06, "epoch": 3.9808, "percentage": 79.74, "elapsed_time": "14:06:56", "remaining_time": "3:35:08"}
313
+ {"current_steps": 312, "total_steps": 390, "loss": 0.448, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "14:09:31", "remaining_time": "3:32:22"}
314
+ {"current_steps": 313, "total_steps": 390, "loss": 0.4229, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "14:13:07", "remaining_time": "3:29:52"}